Step 3.7 Flash
StepFunReleased May 28, 2026
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
- Context window
- 256K tokens
- Max output
- 256K tokens
- Input
- text, image, video
- Output
- text
- Tokenizer
- Other
- Released
- May 28, 2026
- Reasoning
- always on
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $0.200 | $0.0060 | $0.206 |
| Output | $1.15 | $0.034 | $1.18 |
| Cache read | $0.040 | $0.0012 | $0.041 |
Benchmarks
Artificial Analysis
- Intelligence index
- 29.7
- Coding index
- 37.3
- Agentic index
- 21.5
Design Arena
| Category | Elo | Win rate | Rank |
|---|---|---|---|
| 3Dmodels | 1197 | 43.2% | #46 |
| ASCII artmodels | 1227 | 51.5% | #13 |
| Codemodels | 1217 | 45.7% | #44 |
| Data vizmodels | 1212 | 46.7% | #41 |
| Game devmodels | 1207 | 41.6% | #43 |
| SVGmodels | 1122 | 39.8% | #49 |
| UI componentsmodels | 1212 | 44.6% | #44 |
| Websitesmodels | 1225 | 47.1% | #43 |
Head-to-head preference voting. How we filter and rank
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model stepfun/step-3.7-flash.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "stepfun/step-3.7-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="stepfun/step-3.7-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "stepfun/step-3.7-flash",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does Step 3.7 Flash cost via API?
- Through OpenKey, Step 3.7 Flash costs $0.206 per 1M input tokens and $1.18 per 1M output tokens. That is the provider price ($0.200 / $1.15) plus a flat 3% fee — nothing else.
- What is Step 3.7 Flash's context window?
- Step 3.7 Flash accepts up to 256K tokens of context and returns up to 256K tokens per request.
- Is Step 3.7 Flash OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "stepfun/step-3.7-flash" using any OpenAI SDK — only the base URL and API key change.
- What inputs does Step 3.7 Flash support?
- Step 3.7 Flash accepts text, image, video input and produces text output.